Staff Engineer, API Platform

The role

A Staff Engineer will own the end-to-end design and evolution of the model API platform. This includes leading a Python to Go rewrite and managing audio, vision, and streaming infrastructure.

What you will do

• End-to-end design and evolution of the platform
• Leading the Python to Go rewrite by setting architecture and patterns
• Audio pipeline engineering including TTS chunking and VAD-based silence detection
• Vision pipelines for OCR, layout detection, and VLM harnesses
• Streaming infrastructure including WebSocket connections and queue-based batch processing
• Engineering the commercial layer for metering, billing, and rate-limiting
• Ensuring performance and reliability for a multi-tenant platform
• Observability through logging, metrics, and tracing
• Integration testing infrastructure
• Partnering with Inference and MLOps teams to mentor them on production engineering

Required qualifications

• 7+ years building production backend systems at scale
• Strong Go in production
• Comfortable in Python
• Track record of designing and operating high-scale, low-latency, multi-tenant distributed systems
• Hands-on experience with real-time / streaming systems
• Strong PostgreSQL and Redis fundamentals
• Comfort running services on Kubernetes in production
• Judgment of a senior IC

Nice to have

• Experience serving LLMs, ASR, TTS, or vision models in production
• Background in audio processing (pyav, FFmpeg, codec / sample-rate work, VAD)
• Experience building metering, billing, or wallet / payments infrastructure
• Time at an early- or growth-stage startup

About the company

Sarvam is building the bedrock of Sovereign AI for India by developing a full-stack sovereign AI platform. The company works with leading enterprises and public institutions and is backed by Lightspeed, Peak XV, and Khosla Ventures.